© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10533
    Prev
    Next
    INDEX
    Explanations

    terms related to zoning and land use regulations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     reun
    -0.26
     mind
    -0.25
     false
    -0.24
     songs
    -0.23
     painfully
    -0.22
     holy
    -0.22
     UK
    -0.22
     dağı
    -0.21
     ми
    -0.21
     female
    -0.21
    POSITIVE LOGITS
     Autorizaciones
    0.81
     メンテナ
    0.79
    <unused43>
    0.79
    <unused41>
    0.79
    <unused17>
    0.78
    <pad>
    0.78
    <unused74>
    0.78
    <unused79>
    0.78
    <unused42>
    0.78
    <unused3>
    0.78
    Activations Density 0.127%

    No Known Activations